激光杂志
激光雜誌
격광잡지
LASER JOURNAL
2014年
12期
36-39,44
,共5页
图像压缩%最小二乘支持向量机%曲波变换%和声搜索算法
圖像壓縮%最小二乘支持嚮量機%麯波變換%和聲搜索算法
도상압축%최소이승지지향량궤%곡파변환%화성수색산법
image compression%least squares support vector machine%curvelet transform%harmony search algo_rithm
为了提高图像压缩质量，针对传统压缩算法的不足，提出一种曲波变换和最小二乘支持向量机相融合的图像压缩算法。首先采用曲波变换把图像分解为不同尺度和不同方向的曲波系数，并采用熵编码对粗尺度层曲波系数进行压缩，然后利用最小二乘支持向量机对细尺度层中不同方向的曲波系数进行学习，并通过和声搜索算法优化最小二乘支持向量机，实现细尺度层曲波数的压缩，最后采用图像压缩仿真实验测试其性能。结果表明，曲波变换和最小二乘支持向量机相融合的图像压缩算法提高了图像压缩的峰值信噪比，加快了图像压缩的速度，获得了更好的图像压缩效果。
為瞭提高圖像壓縮質量，針對傳統壓縮算法的不足，提齣一種麯波變換和最小二乘支持嚮量機相融閤的圖像壓縮算法。首先採用麯波變換把圖像分解為不同呎度和不同方嚮的麯波繫數，併採用熵編碼對粗呎度層麯波繫數進行壓縮，然後利用最小二乘支持嚮量機對細呎度層中不同方嚮的麯波繫數進行學習，併通過和聲搜索算法優化最小二乘支持嚮量機，實現細呎度層麯波數的壓縮，最後採用圖像壓縮倣真實驗測試其性能。結果錶明，麯波變換和最小二乘支持嚮量機相融閤的圖像壓縮算法提高瞭圖像壓縮的峰值信譟比，加快瞭圖像壓縮的速度，穫得瞭更好的圖像壓縮效果。
위료제고도상압축질량，침대전통압축산법적불족，제출일충곡파변환화최소이승지지향량궤상융합적도상압축산법。수선채용곡파변환파도상분해위불동척도화불동방향적곡파계수，병채용적편마대조척도층곡파계수진행압축，연후이용최소이승지지향량궤대세척도층중불동방향적곡파계수진행학습，병통과화성수색산법우화최소이승지지향량궤，실현세척도층곡파수적압축，최후채용도상압축방진실험측시기성능。결과표명，곡파변환화최소이승지지향량궤상융합적도상압축산법제고료도상압축적봉치신조비，가쾌료도상압축적속도，획득료경호적도상압축효과。
In order to obtain good compression results of image, a novel image compression algorithm combining curvelet transform and least squares support vector machine was proposed in this paper. Firstly, images were decom_posed by curvelet transform to get curvelet coefficients of different scales and orientations, and curvelet coefficients of the coarse scale were compressed by the entropy coding, and then the curvelet coefficients of different detail scales and orientations were learnt by least squares support vector machine and the parameters of least squares support vectors are optimized by harmony search algorithm, finally the performance is test by simulation experiments. The results indicate that the proposed algorithm can images the PSNR and fasten the compression speed, so it can obtain good compression efficient.
